© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20248
    Prev
    Next
    INDEX
    Explanations

    the word "sure" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idas
    -0.69
    foreseen
    -0.67
    ells
    -0.66
    ijah
    -0.66
    IDER
    -0.66
    uscript
    -0.64
    intosh
    -0.64
    AK
    -0.64
    RAFT
    -0.64
    ilaterally
    -0.63
    POSITIVE LOGITS
     there
    0.76
     whoever
    0.72
     someday
    0.72
     glad
    0.70
     nobody
    0.66
     plenty
    0.65
     somebody
    0.64
     someone
    0.63
     ringing
    0.62
     Admin
    0.61
    Activations Density 0.051%

    No Known Activations